© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103145
    Prev
    Next
    INDEX
    Explanations

    grind mill and milling machinery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ligheten
    -0.75
    짚
    -0.69
    らない
    -0.66
     اندروید
    -0.65
    tileno
    -0.65
    Bundles
    -0.65
    бле
    -0.64
    쩔
    -0.64
    istle
    -0.64
     Developed
    -0.64
    POSITIVE LOGITS
     grinding
    4.06
     grind
    4.03
     Grinding
    3.27
    grind
    3.22
     Grind
    3.22
     grinder
    3.05
    Grind
    3.03
     mill
    2.55
     mills
    2.34
     milling
    2.28
    Activations Density 0.051%

    No Known Activations